Beruflich Dokumente
Kultur Dokumente
By
Dr. Muhammad Moinuddin
Course Outline/Contents
Introduction
Biological
Inspiration
Motivation: Applications
Advantages of NN
Learning Methods
Unsupervised Learning
Correlation
Supervised Learning
Error
Fundamentals of NN
Perceptron
Neuron
Synaptic
Weights
Activation Function
Algorithm
Variants
Theorem
Various Algorithms
Vector Quantization
Recurrent NN
Architectures
Feedback structure
Backpropagation Through Time
Hopfield NN
Applications of NN
Function
Approximation/Curve Fitting
Pattern Recognition/Classification
Robots path planning
Network routing algorithms
Time-Series Prediction
Estimation
Optimization
Control
Introduction
A neuron: many-inputs /
one-output unit
output can be excited or not
excited
incoming signals from other
neurons determine if the
neuron shall excite ("fire")
Output subject to
attenuation in the
synapses, which are
junction parts of the neuron
Human Brain
Stimulus
Receptors
Neural Net
Nerve
Effectors
Response
Methodology of NN
How NN Classifies?
a1x+b1y+c1 a3x+b3y+c3
n
ou
gr
ck
Ba
Signal
n
ou
gr
ck
Ba
Signal
a2x+b2y+c2
X
0
1
NN Structure
1. Neurones (nodes)
2. Synapses (weights)
Learning Process
What is Learning
Learning of an ANN
How to adapt Network architecture
Learning method:
Unsupervised
learning
Reinforcement learning
Supervised learning
Learning Steps
Learning Methods
Error correction learning
Memory based learning
Hebbian learning
Competitive learning
Boltzman learning
Hebbian learning
Simple Examples:
Competitive learning
The output of neurons compete to become
active (fired)
Only a single neuron active at any one
time
Example: Self Organizing MAP (SOM)
Reinforcement Learning
Supervised Learning
Example: Back propagation
Desired output of the training examples
Error = difference between actual &
desired output
Change weight relative to error size
Calculate output layer error , then
propagate back to previous layers.